Haibin Xie

Supervised Neural Q_learning based Motion Control for Bionic Underwater Robots

Bionic underwater robots have been a hot research area in recent years. The motion control methods for a kind of bionic underwater robot with two undulating fins are discussed in this paper. The equations of motion for the bionic underwater robot are described. To apply the reinforcement learning to the actual robot control, a Supervised Neural Q_learning (SNQL) algorithm is put forward. This algorithm is based on conventional Q_learning algorithm, but has three remarkable distinctions: (1) using a feedforward neural network to approximate the Q_function table; (2) adopting a learning sample database to speed up learning and improve the stability of learning system; (3) introducing a supervised control in the earlier stage of learning for safety and to speed up learning again. Experiments of swimming straightforward are carried out with SNQL algorithm. Results indicate that the SNQL algorithm is more effective than pure neural Q_learning or supervised control. It is a feasible approach to figure out the motion control for bionic underwater robots.

A Bionic Neural Network for Fish-Robot Locomotion

A bionic neural network for fish-robot locomotion is presented. The bionic neural network inspired from fish neural network consists of one high level controller and one chain of central pattern generators (CPGs). Each CPG contains a nonlinear neural Zhang oscillator which shows properties similar to sine-cosine model. Simulation results show that the bionic neural network presents a good performance in controlling the fish-robot to execute various motions such as startup, stop, forward swimming, backward swimming, turn right and turn left.

Design of a Central Pattern Generator for Bionic-robot Joint with Angular Frequency Modulation

The paper proposes an artificial central pattern generator (CPG) for bionic-robot joint control. The neural oscillator adopted to produce rhythmic pattern is specially designed from original sin-cosine oscillator model. An amplitude neural estimator consisted of two neurons is presented to provide sensor feedback to CPG control. The artificial CPG can adapt itself to the physical system parameters variety by rhythmic movement angular frequency modulation.

Computational Hydrodynamics and Statistical Modeling on Biologically Inspired Undulating Robotic Fins: A Two-Dimensional Study

Undulation fishes, whose propulsion is mainly achieved by undulating ribbon fins, are good at maneuvering or stabilizing at low speeds. This paper suggests and proposes a two-dimensional approximate computational model, which is used to conduct an initial analysis on undulation propulsion scheme. It is believed that this undulating mode has a better potential for exploitation in artificial underwater systems. Hydrodynamics of two-dimensional undulating fins under a series of kinematical parameter sets is explored via numerical simulation. The periodicity of undulation forces and moments is studied. The effects of inlet velocity, wavelength, undulation frequency, and undulation amplitude are investigated. Furthermore, a dimensionless two-parameter model for undulation surge force is established with a given wavelength (in terms of, a single wavelength or a dual wavelength) using statistical method. The work in this paper is able to provide studies on bionic undulation mode. It has also formed a meaningful basis for three-dimensional (3D) hydrodynamics and corresponding control methods in bionic undulation robots.

Dynamics Modeling and Simulation of a Bionic Swim Bladder System in Underwater Robotics

While considering that fish could suspend themselves under water and could enhance their mobility by adjusting its swim bladder, we have carried out research on a bionic swim bladder system in underwater robotics, which could amend the underwater robotics’ static balance and controllability conditions even if the depth of water changes. First, this paper introduces the bio-swim bladder’s structure and function. Second, it works out the dynamic model of the bionic swim bladder, and then it analyses the dynamic characteristic and effect of the bionic swim bladder system with the software Matlab/simulink. Finally, considering about the nonlinear relationship of the parameters in the model, this paper brings forward a dual-speed control method, which could make the effect of the bionic swim bladder non-coupling. The result of the simulation reveals that the bionic swim bladder could change the buoyancy and centroid distribution of the underwater robotics effectively and independently, bringing it into a balance state, under which the control and maneuverability could be enhanced.

Learning Control for Biomimetic Undulating Fins: An Experimental Study

Learning control should focus on imitating natural fish’s adaptability to complex and dynamic environment to some extent, rather than mimicking streamlined shapes or specific actuators to develop more mechanical prototypes. In this paper, an experimental study on a proposed learning control of the robotic undulating fin, RoboGnilos, is suggested and explored. This study takes inspirations from biological world to practical control algorithms. In detail, an iterative learning scheme based control is studied with the cooperation of a filter to reduce the measurement noise, and a curve fitting component to keep the necessary phase difference between neighboring fin rays. Moreover, the iterative learning control algorithm is designed and implemented for practical applications. The experimental results validate that the proposed learning control can effectively improve the propulsion of RoboGnilos. For instance, the steady propulsion velocity may be enhanced by over 40% with some specified parameters.

Dynamic analysis on the bionic propulsor imitating undulating fin of aquatic animals

The undulating fin propulsion mode belonged to one of MPF (median and/or paired fin) has a great potential and a bright prospect because of the remarkable advantages including capable of producing vector thrust, smaller disturbance to ambient flow field, as well as tending to transplant to underwater robots. In this paper, we will introduce a novel bionic propulsor that imitates the structure and function of the undulating fin of aquatic animals, and propose a simplified computational model to analyze the dynamics of the propulsor. The hydrodynamic model of the bionic propulsor including six components of forces and moments is derived theoretically. In addition, the basic relationships between the hydrodynamics of the bionic propulsor with the undulating motion parameters and geometric parameters of the fin surface as well as the velocity induced by its carrier are studied by means of simulation method. At last, the validity of the analytic method presented by the paper and the rationality of its relevant conclusions are preliminarily verified through conducting the thrust and moment test to the bionic propulsor.

Dynamic Analysis of a Novel Artificial Neural Oscillator

This paper proposes a novel artificial neural oscillator consisted of two neurons with excellent control properties. The mutual connections between the neurons are just linear functions and determine the oscillation angular frequency. And each neuron has a nonlinear self-feedback connection to hold up oscillation amplitude. The dynamics of the neural oscillator was modelled with nonlinear coupling functions. And the stability, amplitude, angular frequency of the oscillator are determined independently by three parameters of the functions. Since it has simple structure and favorable control advantages, it can be used in bionic robots locomotion control system. The first application is an artificial central pattern generator (CPG) controller for bionic robots joint. The second is a bionic neural network for fish-robots locomotion control.

Advances and Trends of Bionic Underwater Propulsors

In recent twenty years, tens of the bionic underwater prototype propulsors which imitate aquatic animals have been invented. The bionic principles hand classification of bionic propulsors were presented firstly. The main advance of the bionic propulsors in the world has been listed in table form. Then the bottlenecks which include low efficiency and massive mechanism, hard-shelled reverse control method and exterior hydro-dynamic analysis are discussed. The future trends of the bionic underwater propulsors are forecasted. The main potential breakthroughs include innovative smart actuators and bionic neural control methods.

Bionic bladder based depth control for bionic underwater robots

Depth control of underwater robots is an indispensably function, especially when robots are stationary in water. A bionic bladder system was designed to control the depth of the robots in water. It was composed of a cylinder and a piston. The dynamic models of how the bionic bladder system controls underwater robots were established and based on which a dual-velocity control system was designed. The results of simulation showed that a good control performance could be achieved with proper control parameters. The experiments have been done in water tank to test and validate the performance of the control system.